CN113748030A

CN113748030A - System and method for vehicle tire performance modeling and feedback

Info

Publication number: CN113748030A
Application number: CN202080031191.1A
Authority: CN
Inventors: S·多莱斯瓦米; T·E·韦; J·R·巴尔; A·C·斯托纳克; 托马斯·A·萨姆斯; H·多尔菲; P·高塔姆
Original assignee: Bridgestone Americas Tire Operations LLC
Current assignee: Bridgestone Americas Tire Operations LLC
Priority date: 2019-04-01
Filing date: 2020-03-30
Publication date: 2021-12-03
Anticipated expiration: 2040-03-30
Also published as: CN113748030B; US20220016941A1; EP3946983A1; US20220016940A1; EP4261051A3; EP4261050A3; EP4257376A2; EP4261051A2; JP7329068B2; JP2023145737A; EP4257376A3; EP3946983A4; US20220016938A1; US20220017090A1; WO2020205703A1; US11993260B2; EP4261050A2; CN116890577A; JP2022521836A

Abstract

A computer-implemented system and method for vehicle tire performance monitoring, modeling, and feedback is disclosed. Vehicle data, including movement data and/or location data, is collected for a vehicle and/or at least one tire associated with the vehicle. Determining a current tire wear state of the at least one tire in real time based at least in part on the collected data, various embodiments of which are disclosed herein. One or more tire performance characteristics, such as tire traction, time to replace, and/or future tire wear, are predicted based at least in part on the determined tire wear state and the collected data. Selectively providing real-time feedback based on the predicted one or more tire performance characteristics and/or the determined current tire wear state. The feedback may include an alert to an operator or fleet manager, or may take the form of an automated control invention.

Description

System and method for vehicle tire performance modeling and feedback

Technical Field

The present disclosure relates generally to modeling and predicting tire performance and providing feedback based on the modeling and prediction. More particularly, embodiments of the invention as disclosed herein relate to systems and methods for implementing tire wear and/or tire traction models for wheeled vehicles, including but not limited to motorcycles, consumer vehicles (e.g., passenger cars and light trucks), commercial vehicles, and off-road (OTR) vehicles.

Background

The prediction of tire wear and corresponding tire traction capacity is an important tool for anyone who owns or operates a vehicle, particularly in the context of vehicle fleet management. As tires are used, the tread typically becomes progressively thinner and the overall tire performance changes.

In addition, irregular tread wear may occur for a variety of reasons that may cause a user to replace a tire earlier than would otherwise be required. The vehicle, driver, and individual tires all differ from one another and may cause the tires to wear at very different rates. For example, high performance tires for sports cars wear faster than tires for passenger cars. However, various factors may cause the tire to wear earlier than expected, and/or cause the tire to wear irregularly and produce noise or vibration. Two common causes of premature and/or irregular tire wear are inadequate inflation pressure and out-of-specification alignment conditions.

Tire wear is known to develop in a non-linear manner throughout the life of the tire. One of the main reasons for this is that as the tread wears over time, the tread blocks become stiffer. In addition, the tread pattern is typically designed to have a smaller void area as the tire wears. Either or both of these characteristics may contribute to slower wear rates.

Most tire wear predictions are focused on the initial wear rate, i.e., the rate of wear when the tire is new. This is due, at least in part, to the fact that the tire industry is generally concerned with new tire performance due to the necessity of meeting Original Equipment Manufacturer (OEM) requirements. To predict the performance of a tire over its life, a new wear model is required.

However, tire wear is a complex modeling phenomenon. Accurate models using Finite Element Analysis (FEA) currently exist, but these simulations typically take weeks to complete. If it is desired to simulate wear rates at several different tread depths, this will further take months to perform computationally expensive simulations.

It is desirable to provide users with substantially real-time predictions as to the performance and capabilities of their tires.

It is also desirable to estimate the traction capability of the tire and provide such feedback as input to a model for other useful/functioning prediction or control loops.

It is also desirable to estimate the tread depth of the tire and provide such feedback as an input to a model for other useful/functional predictions, such as, for example, traction, fuel efficiency, durability, etc. Accurate tread depth prediction is the first step in predicting many other tire performance areas.

It is also desirable to provide these services as part of a distributed and relatively automated tire-as-a-service model without the need for manual tread depth measurements (such as would typically be provided by field engineers and/or with dedicated equipment, for example).

It is known to generate high frequency vehicle data and/or tire data for the reason of determining a vehicle condition at a given time. However, continuously collecting streaming data results in data points that are too bulky, which is generally not practical from a data transmission, storage, and processing perspective. It is also desirable to improve knowledge status based on measurements of tread depth, thereby providing real-time feedback to users (e.g., individual drivers, fleet managers, other equivalent end users) based on the improved ability to predict wear life left in a tire based on several periodic measurements, and thereby enabling users to achieve maximum value from the tire.

Disclosure of Invention

In a first exemplary embodiment disclosed herein, the foregoing objects are achieved via a computer-implemented method for modeling and predicting tire performance and providing feedback based on the modeling and prediction. The method comprises the following steps: collecting vehicle data for a vehicle and/or tire data for at least one tire associated with the vehicle; and determining a current tire wear state of the at least one tire in real time based at least in part on the collected data. Predicting one or more tire performance characteristics based, at least in part, on the determined tire wear state and the collected data. Selectively providing real-time feedback based on the predicted one or more tire performance characteristics and/or the determined current tire wear state.

Additional advantageous features are also realized in exemplary variations of the foregoing first embodiment, wherein a second embodiment of a computer-implemented method for estimating a tire wear state is disclosed herein and includes accumulating, in a data storage device, information about a probability distribution corresponding to each tire wear factor of a respective plurality of tire wear factors. Vehicle data and/or tire data including movement data and location data collected in association with the vehicle is transmitted from the vehicle to a remote server. At least one observation corresponding to one or more of the plurality of factors is generated based on the transmitted vehicle data. A bayesian estimate of a tire wear state of at least one tire associated with the vehicle over a given time is generated based at least on the generated at least one observation and the stored information about the probability distribution.

One exemplary aspect of the foregoing second embodiment may include storing information regarding updated probability distributions corresponding to a respective plurality of factors contributing to tire wear of at least one tire associated with the vehicle based at least on the generated at least one observation.

Another exemplary aspect of the foregoing second embodiment may include predicting a tire wear state at one or more future parameters of at least one tire associated with the vehicle. For example, the tire wear state may be predicted with respect to an upcoming vehicle travel time period or with respect to an upcoming travel distance.

Another exemplary aspect of the foregoing second embodiment may include a time to replace at least one tire associated with the vehicle based on a current tire wear state or a predicted tire wear state as compared to a tire wear threshold associated with the at least one tire associated with the vehicle.

In another exemplary aspect of the foregoing second embodiment, the information about the plurality of probability distributions may reflect a time series characterization curve array.

Another exemplary aspect of the foregoing second embodiment may comprise: receiving one or more tire wear input values from a user via a user interface associated with a remote server; and generating at least one observation of one or more of the plurality of factors based on the one or more tire wear input values.

Another exemplary aspect of the foregoing second embodiment may comprise: receiving one or more tire wear input values generated by one or more sensors mounted in or on respective ones of the at least one tire; and generating at least one observation of one or more of the plurality of factors based on the one or more tire wear input values.

Another exemplary aspect of the foregoing second embodiment may comprise: receiving one or more tire wear input values generated by a sensor external to the vehicle; and generating at least one observation of one or more of the plurality of factors based on the one or more tire wear input values.

In another exemplary aspect of the foregoing second embodiment, at least one of the tire wear input values generated by the sensor external to the vehicle comprises a tread depth measurement.

Another exemplary aspect of the foregoing second embodiment may include generating an estimated tire wear state using the baseline value and a range corresponding to the estimated confidence level.

A system for estimating a state of tire wear may be provided according to the second embodiment described above. The system may include a data storage network having information stored thereon regarding a probability distribution corresponding to each tire wear factor of a respective plurality of tire wear factors. For each of the plurality of vehicles, the distributed computing node is linked to one or more on-board sensors respectively configured to collect vehicle data. A server-based computing network is provided that includes a computer-readable medium having instructions resident thereon that are executable by one or more processors to direct the performance of the aspects previously described with respect to the second embodiment.

Additional advantageous features are also realized in another exemplary variation of the first embodiment described above, wherein a third embodiment of a computer-implemented method for analyzing a tire wear model using a brush model is disclosed herein. The brush model is a simplified tire model that models tread elements as individual "bristles," which greatly reduces the complexity of modeling the contact interface between the road and the rubber. The model may capture the first order effects (tread block hardening and contact area increase) that occur in a real tire as it wears.

According to a third exemplary embodiment, an initial tread depth of a tire associated with a vehicle is determined, and an initial wear rate of the tire is determined based at least in part on the initial tread depth. One or more tire conditions are measured as a time series input to a predictive tire wear model. The current wear rate is normalized based on this input regarding the initial wear rate of the tire, where the tire wear state of the tire may be predicted for one or more specified future parameters.

In one aspect of the foregoing third embodiment, the current wear rate is determined based at least in part on a brush tire wear model for a contact interface between a base material of the tire and a road surface, where the interface is represented as a plurality of independently deformable elements.

In another aspect of the foregoing third embodiment, the measured one or more tire conditions include a detected contact area and a void area corresponding to a tire tread depth.

In another aspect of the foregoing third embodiment, the one or more specified future parameters are associated with a travel time.

Alternatively, one or more specified future parameters may be associated with the distance traveled.

In another aspect of the foregoing third embodiment, the time for replacement of a tire may be predicted based on a predicted tire wear state as compared to one or more predetermined tire wear thresholds associated with the tire.

In another aspect of the foregoing third embodiment, an alert is generated to a user associated with the vehicle based on the predicted replacement time.

In another aspect of the foregoing third embodiment, the one or more measured conditions are received from a user via a user interface.

In another aspect of the foregoing third embodiment, one or more of the measured conditions are generated by and received from one or more sensors mounted in or on the tire.

In another aspect of the foregoing third embodiment, the one or more measured conditions are generated by and received from a sensor external to the vehicle. At least one of the tire wear input values generated by the sensors external to the vehicle may comprise a tread depth measurement.

In another aspect of the foregoing third embodiment, a tire rotation threshold event and/or an alignment threshold event may be predicted by the system based at least in part on the time series input and/or the predicted tire wear state. Accordingly, an alert may be generated to a user interface associated with the vehicle based thereon. The user interface may be a static display installed in the vehicle, a display for a mobile computing device associated with a driver of the vehicle, or the like.

In another aspect of the foregoing third embodiment, an optimal tire type of the vehicle may be predicted based at least in part on the time series input and/or the predicted tire wear state. Accordingly, an alert may be generated to a user interface associated with the vehicle based thereon. The user interface may be a static display installed in the vehicle, a display for a mobile computing device associated with a driver of the vehicle, or the like.

In one embodiment, a system for predicting the progress of vehicle tire wear in accordance with the foregoing third embodiment may be provided, the system comprising a server functionally linked to a data storage network. The data storage network includes an original tread depth of a tire associated with the vehicle and a predictive tire wear model. One or more sensors are provided and configured to provide signals corresponding to measured tire conditions. The server is configured to determine an initial wear rate of the tire based on the original tread depth and the tire wear model, collect signals corresponding to the measured tire condition as a time series input to the predictive tire wear model, normalize a current wear rate to the initial wear rate of the tire based on the input, and predict a tire wear state of the tire for one or more specified future parameters.

In one exemplary aspect of the system according to the third embodiment, the wear rate may be modeled using a brush tire wear model for the contact interface between the base material of the tire and the road surface, where the interface is represented as a plurality of independently deformable elements. Alternative physics-based tire wear models are also contemplated within the scope of the present disclosure, including but not limited to FEA models.

Additional advantageous features are also realized in the exemplary variation of the first embodiment described above, wherein a fourth embodiment of a computer-implemented method for estimating the progress of vehicle tire wear is disclosed herein. A method according to a fourth embodiment includes storing a tread depth of a tire associated with a vehicle over a first (e.g., initial or unworn) stage. The method also includes sensing and storing, at a first stage, a first set of one or more modal frequencies of the tire in response to an impact associated with the first modal analysis. Over a second, subsequent (e.g., at least partially worn) phase, a second set of corresponding one or more modal frequencies of the tire is sensed in response to an impact associated with the second modal analysis. Based on the calculated frequency shift between the at least one corresponding modal frequency from each of the first and second sets, a tire wear state of the tire may be estimated over the second stage.

In one exemplary aspect of the foregoing fourth embodiment, the mass of the tire is stored over a first phase, wherein the step of estimating the tire wear state over a second phase includes determining a change in the mass of the tire between the first phase and the second phase based on the calculated frequency shift.

In another exemplary aspect of the foregoing fourth embodiment, the estimated loss of tire tread is determined relative to a change in the mass of the tire between the first stage and the second stage based on the calculated frequency shift. Alternatively, the estimated loss of tire tread may be determined via a retrievable correlation between the observed frequency shift and the change in tire tread for a given tire. The correlation may be retrieved from a data storage device, for example, for a given tire type, or may be established over time based on historical measurements of changes in the tire tread and the shift between corresponding modal frequencies associated with a given tire type.

In another exemplary aspect of the foregoing fourth embodiment, the first and second sets of corresponding modal frequencies are sensed via one or more accelerometers mounted in association with the tire in response to excitation of a structural mode of the tire. One or more accelerometers may be attached to the tire, for example on the inner liner of the tire, or may be mounted to the spindle of an associated vehicle.

In another exemplary aspect of the foregoing fourth embodiment, tire structure modes are randomly excited during operation of the tire and associated output signals generated by the one or more accelerometers are captured.

In another exemplary aspect of the foregoing fourth embodiment, the tire structural mode is excited by a controlled impact of an external object (such as, for example, a hammer) on the tire.

In another exemplary aspect of the foregoing fourth embodiment, the tire structure pattern is activated by directing movement of the vehicle relative to one or more predetermined obstacles (such as, for example, cleats or speed bumps) or roads that include sufficiently rough surfaces.

An exemplary system according to a fourth embodiment as disclosed herein may enable vehicle tire wear estimation via a server or server network functionally linked to a data storage network and one or more sensors mounted on the tire and/or vehicle, for example according to any one or more of the preceding embodiments and aspects thereof.

Additional advantageous features are also realized in the exemplary variations of the first embodiment described above, wherein a fifth embodiment of a computer-implemented method for estimating vehicle tire wear is disclosed herein. The method of the fifth embodiment includes generating first data corresponding to real-time dynamics of the vehicle and/or at least one tire of a plurality of tires supporting the vehicle with one or more sensors associated with the vehicle and/or at least one tire. The first data is processed locally to generate second data as a reduced subset of the first data, where the second data represents the first data and includes any one or more predetermined features extracted therefrom. The second data is selectively transmitted to a remote computing system via a communication network, and the remote computing system processes the second data and any one or more extracted features to estimate a wear characteristic of the at least one tire.

The second data may include a plurality of sequential data frames, each data frame including a multi-dimensional histogram of forces associated with the vehicle and/or the at least one tire.

In an exemplary aspect of the foregoing fifth embodiment, the method further comprises: selecting a subset of the data frames at least between the first event and the second event; and summarizing the data frames at a specific time or within a specific distance.

In another exemplary aspect of this fifth embodiment, the aggregation of the data frames is performed via local processing prior to transmission of the aggregated data frames to the remote computing system. Alternatively, a subset of the data frames may be transmitted to a remote computing system, where the aggregation of the data frames is performed via the remote computing system.

In another exemplary aspect of this fifth embodiment, the method further comprises correcting for missing data in the summarized data frames by scaling the summarized data frames by an expected number of data frames relative to an actual collected number of data frames.

The extracted features of the second data may comprise wear performance characteristics indicative of vehicle driving behaviour.

Processing the first data may include fourier transforming the first data and generating second data including the extracted correlated frequencies and associated amplitudes.

In another exemplary aspect of the fifth embodiment, the second data includes aggregated low frequency CAN data corresponding to an amount of time the vehicle spends in each of the one or more representative driving conditions.

In another aspect of the fifth embodiment, the first data includes a CAN bus signal. The second data is generated via an encoding neural network layer, the third data is generated via a decoding neural network layer, and a wear calculation layer is appended to an output of the decoding neural network layer and configured to transform the decoded CAN bus signal into an instantaneous estimated wear value for the at least one tire.

In an exemplary aspect of the foregoing fifth embodiment, the method further comprises: comparing the estimated wear value and the actual wear value of the at least one tire to generate an error value; and providing the error value as feedback to the neural network layer.

In another aspect of the fifth embodiment, the selective transmission of the second data is automated and event-based, rather than relying on manual selection of the transmission. Alternatively, the selective transmission of the second data may be time-based.

In another aspect of the fifth embodiment, a method for estimating vehicle tire wear is implemented using one or more sensors associated with at least one tire of a plurality of tires of a vehicle and/or a support vehicle, wherein first data corresponding to real-time dynamics of the vehicle and/or the at least one tire is generated. Low frequency second data corresponding to the vehicle location is generated via the global positioning system transceiver. The second data is selectively transmitted to a remote computing system via a communication network, wherein the second data is processed in accordance with the vehicle model and one or more vehicle route characteristics to generate third data corresponding to the first data, and the third data is also processed to estimate a wear characteristic of the at least one tire.

In an exemplary aspect of the foregoing fifth embodiment, the second data further comprises a plurality of sequential data frames, each data frame comprising a multi-dimensional histogram of forces associated with the vehicle and/or the at least one tire remote computing system. The remote computing system reconstructs the vehicle route from the collected vehicle position data and provides vehicle route feedback into the corresponding multi-dimensional histogram.

Additional advantageous features are also realized in the exemplary variations of the first embodiment described above, wherein a sixth embodiment of a computer-implemented method for estimating vehicle tire wear is disclosed herein. First data is generated via one or more sensors associated with the vehicle and/or at least one tire of a plurality of tires supporting the vehicle, the first data corresponding to real-time dynamics of the vehicle and/or at least one tire. The first data is processed via a computing system on the vehicle to generate second data as a reduced subset of the first data, the second data representing the first data and including any one or more predetermined features extracted therefrom. The in-vehicle computing system also processes the second data to estimate a wear characteristic of the at least one tire, and generates a notification associated with the estimated wear characteristic to a computing device associated with a user of the vehicle.

In an exemplary aspect of the foregoing sixth embodiment, the step of processing the second data to estimate a wear characteristic of the at least one tire comprises: processing the second data to generate third data corresponding to the first data; and also processing the third data to estimate a wear characteristic of the at least one tire.

In another exemplary aspect of the foregoing sixth embodiment, the first data comprises a CAN bus signal, the second data is generated via an encoding neural network layer, the third data is generated via a decoding neural network layer, and the wear calculation layer is appended to an output of the decoding neural network layer and is configured to transform the decoded CAN bus signal into an instantaneous estimated wear value for the at least one tire.

Another exemplary aspect of the foregoing sixth embodiment further comprises: comparing the estimated wear value and the actual wear value of the at least one tire to generate an error value; and providing the error value as feedback to the neural network layer.

Additional advantageous features are further realized in an exemplary variation of any of the first through sixth embodiments described above, wherein a seventh embodiment of a computer-implemented method for estimating and applying a vehicle tire traction state is disclosed herein. The method according to the seventh embodiment may comprise: collecting vehicle data (e.g., including movement data and location data) associated with a first vehicle; and determining a tire wear state of at least one tire associated with the vehicle. One or more tire traction characteristics of at least one tire are predicted based at least on the transmitted vehicle data and the determined tire wear state, and one or more vehicle operation settings are selectively modified based at least on the predicted one or more tire traction characteristics.

In one exemplary aspect of the seventh embodiment described above, the maximum speed of the vehicle is determined based at least on the transmitted vehicle data and the determined tire wear state of each tire associated with the vehicle.

In another exemplary aspect of the seventh embodiment described above, the maximum speed is provided to an autonomous vehicle control system associated with the vehicle. Alternatively, the maximum speed may be provided to a driver assistance interface associated with the vehicle.

In another exemplary aspect of the seventh embodiment described above, the one or more tire wear input values are received from a user via a user interface.

In another exemplary aspect of the above seventh embodiment, the step of determining a tire wear state includes receiving one or more tire wear input values generated by one or more sensors mounted in or on respective ones of the at least one tire. Alternatively, one or more tire wear input values may be generated by sensors external to the vehicle.

In another exemplary aspect of the seventh embodiment described above, the step of determining a tire wear state includes predicting one or more tire wear input values based at least on the transmitted vehicle data and tire data generated by one or more sensors mounted in or on respective ones of the at least one tire.

A system for performing the method according to the seventh embodiment described above and optionally also according to certain exemplary aspects may be provided, the system comprising a remote server functionally linked to the vehicle via a communication network, wherein the vehicle data is transmitted from the vehicle to the remote server. The remote server is configured to provide the one or more predicted tire traction characteristics to an active safety unit associated with the vehicle, and the active safety unit is configured to modify one or more vehicle operation settings based at least on the predicted one or more tire traction characteristics.

In one exemplary aspect of the system according to the seventh embodiment, the active safety unit may comprise an automated braking system associated with the vehicle, and the remote server is configured to provide one or more parameters of the predicted μ -slip curve associated with the respective tire to the automated braking system.

In another exemplary aspect of the system according to the seventh embodiment, the user interface is associated with a remote server and is configured to receive one or more tire wear input values from a user.

In another exemplary aspect of the system according to the seventh embodiment, the remote server is configured to determine a maximum speed of the vehicle based at least on the transmitted vehicle data and the determined tire wear state of each tire associated with the vehicle, and provide the maximum speed to a driver assistance interface associated with the vehicle.

In other exemplary aspects of the system according to the seventh embodiment, the active safety unit may comprise a collision avoidance system and/or an autonomous vehicle control system.

Another example of a system may perform a method according to the seventh embodiment as described above for each vehicle of the plurality of vehicles and optionally also according to certain exemplary aspects associated therewith. The system includes a first remote server functionally linked to the vehicle via a communication network, a fleet management server functionally linked to the first remote server, and a vehicle control system associated with each of the plurality of vehicles. For each of the plurality of vehicles, vehicle data is transmitted from the respective vehicle to a remote server, the first remote server is configured to provide one or more predicted tire traction characteristics to a fleet management server, and the fleet management server is configured to interact with the respective vehicle control system to modify one or more vehicle operation settings based at least on the predicted one or more tire traction characteristics.

In an exemplary aspect of the system, the user interface is associated with a remote server and/or fleet management server and/or vehicle control system and is configured to receive one or more tire wear input values from a user.

In another exemplary aspect of the system, the fleet management server is configured to determine a maximum speed of the given vehicle based at least on the transmitted vehicle data and the determined tire wear state of each tire associated with the respective vehicle, and provide the maximum speed to a vehicle control system associated with the vehicle.

In another exemplary aspect of the system, the fleet management server is configured to calculate a stopping distance potential for a given vehicle based at least on the transmitted vehicle data and the determined tire wear status for each tire associated with the vehicle, and provide the stopping distance potential to a vehicle control system associated with the vehicle.

In another exemplary aspect of the system, the fleet management server is further configured to determine an optimal headway distance for each of the plurality of vehicles associated with the in-order vehicle fleet and transmit the determined optimal headway distance for each of the plurality of vehicles to the respective vehicle control system.

In another exemplary aspect of the system, the fleet management server is configured to determine a maximum speed and/or stopping distance potential for a given vehicle based at least on the transmitted vehicle data and the determined tire wear state for each tire associated with the respective vehicle, determine whether the vehicle meets a threshold traction characteristic, and interact with the vehicle control system to prevent deployment or otherwise refrain from using the respective vehicle if the vehicle does not meet the threshold traction characteristic.

Various ones of the above-described embodiments may be readily combined with one another in the systems and/or methods disclosed herein.

For example, the skilled person will appreciate that the predicted tire wear according to the third or fourth embodiment may be provided as an output of the traction model according to the seventh embodiment, complementary to each other, without modifying the scope of the respective steps or features.

Additionally, one skilled in the art can appreciate that the extracted data according to the fifth embodiment can be provided as an input to a tire wear model according to one or more other embodiments disclosed herein.

Drawings

Hereinafter, embodiments of the present invention are shown in more detail with reference to the accompanying drawings.

Fig. 1 is a block diagram representing an exemplary embodiment of a system according to various embodiments disclosed herein.

FIG. 2 is a block diagram representing an exemplary pull estimation model.

FIG. 3 is a graphical diagram representing an exemplary set of traction characteristics generated by a model as disclosed herein.

FIG. 4 is a graphical diagram representing another set of exemplary traction characteristics generated by a model as disclosed herein.

FIG. 5 is a graphical diagram representing an exemplary set of tire wear (e.g., tread) state values for a fleet of autonomous vehicles.

FIG. 6 is a graphical diagram representing an exemplary application of tire wear (e.g., tread) condition values and predicted tire traction values for a truck fleet.

Fig. 7 is a graphical diagram illustrating the effect of signal resolution on wear rate estimation in the case of using signals collected during a mixed situation of urban and highway vehicle routes.

Fig. 8 is a graph illustrating the effect of signal resolution on wear rate estimation in the case of using signals collected mainly during urban routes.

FIG. 9 is a graphical diagram representing an exemplary method for vehicle dynamics data aggregation and compression into a histogram data frame.

FIG. 10 is a graphical diagram representing an exemplary histogram data frame according to the process of FIG. 9.

FIG. 11 is a graphical diagram representing an exemplary process for histogram data summarization.

FIG. 12 is a graphical diagram representing an exemplary process for histogram data frame scaling to correct missing or incomplete data.

FIG. 13 is a graphical diagram representing an exemplary tire wear modeling flow.

FIG. 14 is a graphical diagram representing an exemplary real-time model integration of a tire wear modeling flow in accordance with FIG. 13.

FIG. 15 is a graphical diagram illustrating an exemplary neural network autoencoder application to tire wear.

FIG. 16A is a graphical diagram representing exemplary results of neural network auto-encoder compression and decompression of x-axis acceleration data according to the example of FIG. 15.

FIG. 16B is a graphical diagram representing exemplary results of neural network auto-encoder compression and decompression of y-axis acceleration data according to the example of FIG. 15.

FIG. 16C is a graphical diagram representing exemplary results of neural network auto-encoder compression and decompression of vehicle speed data according to the example of FIG. 15.

FIG. 17 is a block diagram representing a conventional method for tire wear analysis (e.g., using vehicle alignment data).

FIG. 18 is a block diagram representing an exemplary Bayesian method for tire wear estimation.

FIG. 19 is a graphical diagram representing an exemplary tire wear model correction.

FIG. 20 is a graphical diagram representing an exemplary application of a Monte Carlo simulation to establish a set of toe-angle distributions.

FIG. 21 is a graphical diagram representing an exemplary application of a Monte Carlo simulation to establish a set of camber angle distributions.

FIG. 22 is a graphical diagram representing an exemplary set of wear progress curves for a front tire.

FIG. 23 is a graphical diagram representing an exemplary set of wear progress curves for a rear tire.

FIG. 24 is a graphical diagram representing an exemplary brush model for wear output.

FIG. 25 is a graphical representation of an exemplary tire wear model prediction compared to measured data.

FIG. 26 is a graphical representation of the difference between tire wear model predictions as disclosed herein and various indoor wear test results for the same control tire.

FIG. 27 is a graphical representation of exemplary results of static natural frequency testing of a given tire in both new and worn states.

FIG. 28a is a graphical representation of an exemplary result from a cleat impact simulation for a tire in a new condition.

FIG. 28b is a graphical representation of an exemplary result from a cleat impact simulation of a tire under wear.

FIG. 29 is a graphical diagram representing exemplary results of a tire from a transmissibility test in both a new condition and a worn condition.

Detailed Description

Referring generally to fig. 1-29, various exemplary embodiments of the present invention may now be described in detail. In the case where various drawings may describe embodiments sharing various common elements and features with other embodiments, similar elements and features are given the same reference numerals, and redundant description thereof may be omitted hereinafter.

Various embodiments of the system as disclosed herein may include a centralized computing node (e.g., a cloud server) in functional communication with a plurality of distributed data collectors and computing nodes (e.g., associated with individual vehicles) to effectively implement the wear and traction model as disclosed herein. Referring initially to fig. 1, an exemplary embodiment of the system 100 includes a computing device 102 on-board a vehicle and configured to at least obtain data and transmit the data to a remote server 130 and/or perform related calculations as disclosed herein. The computing device may be portable or otherwise modular as part of a distributed vehicle data collection and control system (as shown), or may be provided integrally with respect to a central vehicle data collection control system (not shown). The apparatus may include a processor 104 and a memory 106 having program logic 108 resident thereon. In general, a system as disclosed herein may implement many components distributed across one or more vehicles, such as, but not necessarily associated with a fleet management entity, and may also implement a central server or server network in functional communication with each of the vehicles via a communication network. The vehicle components may generally include, for example, one or more sensors linked to a Controller Area Network (CAN) bus network and providing signals therefrom to a local processing unit, such as, for example, body accelerometers, gyroscopes, Inertial Measurement Units (IMUs), position sensors such as Global Positioning System (GPS) transponder 112, Tire Pressure Monitoring System (TPMS) sensor transmitters 118 and associated onboard receivers, and the like. For illustrative purposes, and without otherwise limiting the scope of the invention, the illustrated embodiment includes an ambient temperature sensor 116, an engine sensor 114 configured to provide, for example, a sensed barometric pressure signal, and a DC power supply 110.

Other sensors for collecting and transmitting vehicle data, such as relating to speed, acceleration, braking characteristics, etc., will become sufficiently apparent to those of ordinary skill in the art from the following discussion and will not be discussed further herein. Various bus interfaces, protocols, and associated networks are well known in the art for communicating vehicle dynamics data and the like between respective data sources and local computing devices, and those skilled in the art will recognize a wide range of such tools and means for implementing such tools.

The system may include additional distributed program logic, such as, for example, resident on a fleet management server or other computing device 140, or a user interface of a device for real-time notification (e.g., via visual and/or audio indicators) resident on the vehicle or associated with its driver (not shown), where the fleet management device is functionally linked to the in-vehicle device via a communication network in some embodiments. The system programming information may be provided on-board the vehicle by the driver or from a fleet manager, for example.

In embodiments, the vehicle and tire sensors are also provided with unique identifiers, wherein the onboard device processor 104 can distinguish between signals provided from respective sensors on the same vehicle, and further wherein the central server 130 and/or fleet maintenance supervisor client device 140 can distinguish between signals provided from tires on multiple vehicles and associated vehicles and/or tire sensors, in certain embodiments. In other words, in various embodiments, the sensor output values may be associated with a particular tire, a particular vehicle, and/or a particular tire-vehicle system for purposes of on-board or remote/downstream data storage and implementation of calculations as disclosed herein. The in-vehicle device processor may communicate directly with the hosting server, as shown in fig. 1, or alternatively, the driver's mobile device or the truck-mounted computing device may be configured to receive and process/transmit the in-vehicle device output data to the hosting server and/or fleet management server/device.

The signals received from a particular vehicle and/or tire sensor may be stored in an onboard device memory, or in an equivalent data storage unit functionally linked to an onboard device processor, for selective retrieval as needed for calculation in accordance with the methods disclosed herein. In some embodiments, raw data signals from the various signals may be transmitted from the vehicle to the server in substantially real time. Alternatively, particularly in light of inefficiencies inherent in the continuous data transmission of high frequency data, the data may be, for example, compiled, encoded and/or aggregated for more efficient (e.g., periodic time-based or alternatively defined event-based) transmission from the vehicle to a remote server via an appropriate communication network.

The vehicle data and/or tire data, once transmitted to the escrow server 130 via the communication network, may be stored, for example, in a database 132 associated therewith. The server may include or otherwise be associated with a tire wear model and a tire traction model 134 for selectively retrieving and processing vehicle data and/or tire data as appropriate inputs. The model may be implemented, at least in part, via an executing processor, enabling selective retrieval of vehicle data and/or tire data, and also enabling electronic communication to input any additional data or algorithms from a database, look-up table, or the like stored in association with the server.

In one embodiment of the method disclosed herein, the system 100 as described above may be implemented for modeling and prediction of tire performance and providing feedback based on the modeling and prediction. The method may include collecting vehicle data, including movement data and/or location data, of a vehicle and/or at least one tire associated with the vehicle, and determining a current tire wear state of the at least one tire in real time based at least in part on the collected data. Predicting one or more tire performance characteristics based, at least in part, on the determined tire wear state and the collected data. Selectively providing real-time feedback based on the predicted one or more tire performance characteristics and/or the determined current tire wear state. In various embodiments as disclosed herein, some or all of these steps may be extended as discussed below to provide additional advantages.

For example, referring next to fig. 2, embodiments of the systems and methods as disclosed herein implement a simplified model 134B of a tire, along with a wear state 150 of the tire, to predict a traction capability 160 of the tire, which is relayed to a user to facilitate safe driving. The simplified model predicts forces and moments on the tire at a given friction, load, inflation pressure, speed, etc. For purposes of illustration, the terms "tire wear" and "tread wear" are used interchangeably herein.

In order for the traction model 134B to be accurate, particularly in wet conditions, the tread depth 150 must be known/estimated. This may be accomplished by any of several exemplary techniques as follows.

In one embodiment, tire wear (tread) measurements 150 may be made manually by a user and provided as user input into an application or equivalent interface associated with the in-vehicle computing device 102 or directly with the hosted server 130. The interface may, for example, enable a user to directly input a wear value for a selected tire from a plurality of tires mounted on the identified vehicle. Alternatively, the interface may be configured to prompt the user for a captured image associated with the tread profile or an alternative input, wherein the wear value may be indirectly determined by the user input.

In another embodiment, tire wear measurements 150 may be made by tire-mounted sensors and provided to a hosted server without input, for example, from a user. Such sensors may be mounted, for example, directly in the tire tread or on the tire innerliner.

In another embodiment, tire wear measurements 150 may be provided via one or more sensors external to the vehicle and sent again to cloud server 130 without input, for example, from a user. As one example, the one or more sensors may include a traffic optical sensor comprising: a laser transmitter configured to capture tire tread information by projecting laser light onto or onto a surface of a tire passing the sensor; and one or more laser receiving elements configured to capture the reflected energy and thereby obtain a profile of the tire from which the tire tread can be determined.

In another embodiment, as represented, for example, in fig. 2 and examples of which are provided below in various embodiments, the tire wear value 150 may be estimated based on the wear model 134A. The wear model may include a "digital twin" virtual representation of various physical parts, processes, or systems, where digital and physical data are paired and combined with a learning system such as, for example, a neural network. For example, the real data 136 and associated location/route information from the vehicle may be provided to generate a digital representation of the vehicle tires for estimating tire wear, where subsequent comparisons of the estimated tire wear to the determined actual tire wear may be implemented as feedback to a machine learning algorithm. The wear model 134A may be implemented at the vehicle for processing via the on-board system 102, or the tire data 138 and/or vehicle data 136 may be processed to provide representative data to the hosting server 130 for remote wear estimation.

A tire wear state (e.g., tread depth) 150 as shown in fig. 2 may be provided as an input to a traction model 134B, for example, along with certain vehicle data 136, which may be configured to provide an estimated traction state 160 or one or more traction characteristics 160 for the respective tire. As with the aforementioned wear models, the traction model may include a "digital twin" virtual representation of a physical part, process, or system, where the digital and physical data are paired and combined with a learning system such as, for example, an artificial neural network. The real vehicle data 136 and/or tire data 138 from a particular tire, vehicle, or tire-vehicle system may be provided throughout the life cycle of the respective asset to generate a virtual representation of the vehicle tires for estimating tire traction, wherein subsequent comparisons of the estimated tire traction with corresponding measured or determined actual tire traction may preferably be implemented as feedback to a machine learning algorithm executed at the server level.

In various embodiments, the traction model 134B may utilize an associated combination of results from previous tests (including, for example, stopping distance test results, tire traction test results, etc.) as collected with many tire-vehicle systems, as well as values of input parameters (e.g., tire tread, inflation pressure, road surface characteristics, vehicle speed and acceleration, slip rate and angle, normal force, brake pressure, and load), where tire traction output may be effectively predicted for a given set of current vehicle data and tire data inputs.

In one embodiment, the output 160 from the traction model 134B may be incorporated into an active safety system. As previously described, data is being collected from sensors on the vehicle to feed into the tire wear model 134A, which will predict the tread depth 150, and this will be fed into the traction model 134B. The term "active safety system" as used herein may preferably encompass such systems generally known to those skilled in the art, including, but not limited to, examples such as collision avoidance systems, Advanced Driver Assistance Systems (ADAS), anti-lock braking systems (ABS), etc., which may be configured to utilize traction model output information 160 to achieve optimal performance. For example, collision avoidance systems are typically configured to take evasive action, such as automatically engaging the brakes of the host vehicle to avoid or mitigate a potential collision with the target vehicle, and enhanced information regarding the traction capabilities of the tires, and thus the braking capabilities of the tire-vehicle system, is highly desirable.

Referring to the exemplary models shown in fig. 3 and 4, each graph includes two curves representing the same hypothetical tire at different levels of wear. As can be seen, as the tire wears, the wet traction performance deteriorates accordingly. During inclement weather, there is a critical speed for the worn tire, where the user is at risk of skidding. With the traction model remotely linked to an on-board display or equivalent user interface, the maximum speed can be communicated to the user to provide safer driving conditions.

Traction output information determined from the respective wear state, such as, for example, a μ -slip curve (see, e.g., fig. 4), may also be fed into the active safety system for vehicle control implementation and thereby optimized performance. The slip ratio is expressed ((vehicle speed-tire rotation speed)/vehicle speed), where a slip ratio of 0% corresponds to a free rolling tire and a slip ratio of 100% corresponds to a locked wheel. When the tire μ -slip curve shape changes over time from a "new tire" curve to a "worn tire" curve as represented in fig. 4, the active safety system may preferably be configured to determine what, if any, changes may be made to improve the tire-vehicle performance characteristics. Different μ -slip curves can be considered to have relevant shape and position characteristics that affect the ability of an active safety system (e.g., ABS) to optimize performance, where, for example, the corresponding peak amplitude "μ" is generally understood to affect stopping distance (higher is better). Other relevant characteristics of the mu-slip curve shape may include, for example, slip ratio at the y-axis (mu) peak of the curve, curvature at or near the peak, initial slope of the curve, and the like.

In another embodiment, the ride-sharing autonomous fleet may use the output data 160 from the traction model 134B to disable or otherwise selectively refrain from using a vehicle with a low tread depth during inclement weather, or possibly limit the maximum speed of the vehicle. Referring to the exemplary model as represented in fig. 3, it may be noted that a tire having a "worn" condition is identified as having a slip critical speed of about 55 miles per hour at which the peak coefficient of friction falls below the same threshold, as compared to a tire having a "new" condition that may exceed 100 miles per hour without the peak coefficient of friction falling below the threshold 0.25. Thus, the system may limit the speed of a vehicle that includes one or more tires worn to such a state. If the vehicles are part of a ride-sharing autonomous fleet of vehicles, and the user is seeking to ride during severe weather conditions along a route that requires an increased minimum (e.g., highway) speed, the system may be configured to disable deployment of vehicles that are below a particular tread depth or otherwise have insufficient traction capacity. As shown in fig. 5, an exemplary autonomous vehicle fleet may include a number of vehicles having different minimum tread state values, where the fleet management system may be configured to disable deployment of vehicles that fall below a minimum threshold. The system may be configured to function according to a minimum tire tread value for each of a plurality of tires associated with the vehicle, or in one embodiment, an aggregate tread state for the plurality of tires may be calculated for comparison to a minimum threshold value.

In another embodiment, the fleet management system may implement the output data 160 from the traction model 134B for defined vehicle queues, such as to better optimize the following distance of each tire to achieve maximum fuel savings by better understanding its stopping distance potential. Those skilled in the art will appreciate that minimizing the following distance may result in a reduction in aerodynamic drag of all vehicles in the fleet, and thereby improve the corresponding fuel economy, particularly where more than two trucks are included in the fleet, and that the disclosed improvements to vehicle fleet driving methods may advantageously result in a reduction in following distance over more conventional "one-size-fits-all" methods. Most fuel savings are typically available at following distances of less than about 20 meters, which may be difficult or impossible to maintain during bad weather using conventional techniques for determining traction/braking capability. By more efficiently determining safe headway, the percentage of time spent in queue travel may be increased even in severe weather conditions.

In one embodiment, the active safety or fleet spacing information may be provided to a vehicle braking control system or vehicle fleet travel control system 120 associated with each respective vehicle. In the context of a vehicle fleet, a single vehicle associated with the fleet may receive the following distance information and/or certain vehicle control information and communicate that information to other vehicles in the fleet via other conventional vehicle-to-vehicle communication systems and protocols. The following distance information provided by the system as disclosed herein may be considered a nominal or minimum effective following distance setting, for example, based on the respective traction states of the vehicles in the fleet, it being understood that the vehicle fleet travel control system for a given vehicle or fleet of vehicles may further modify the following distance setting based on monitored traffic events, road conditions, and other environmental conditions that may be outside the traction state determination range of a given embodiment. For example, the first inter-vehicle distance acceptable for a given vehicle under normal driving conditions may necessarily increase based on monitored real-time events, such as a change in the grade of the road to be traversed, or an increased risk of braking events for any one or more vehicles in the fleet.

The components of the vehicle fleet travel control system 120 are generally known in the art and may include, for example, a vehicle braking control system, a collision mitigation system, vehicle-to-vehicle communications, and one or more sensors collectively configured to monitor vehicle data, such as the current headway of the host vehicle (relative to another vehicle in the fleet or non-fleet target vehicle), the respective type of the target vehicle, the relative acceleration or deceleration value of the host vehicle, the pressure value of the brake actuator relative to the host vehicle, and so forth.

As previously described, various embodiments of the method may estimate the tire wear value 150 based on the wear model 134A. Current wear models require several inputs on the system to accurately predict the wear life of the tire and are developed using very high frequency data. However, transmitting high frequency data from distributed data collectors (e.g., associated with individual vehicles) to a centralized computing node (e.g., a cloud server) is too expensive in scale.

Reference is made to fig. 7 and 8 for illustrative purposes, where data is presented showing the effect of signal resolution on wear rate estimation. To construct these graphs, the source data is downsampled to reduce the resolution of the data. The down-sampling in these examples is performed by simply decimating the source data. The source data has a resolution of one meter per sample in the distance domain or about 20Hz at a speed of 45 mph. The x-axis represents the range of one meter per sample to one kilometer per sample. The y-axis shows the relative error in the wear estimate.

In both figures, the data sets correspond to all four tires of a Toyota Camry front wheel drive vehicle using the Turanza EL400 four season tire, respectively. In fig. 7, the data represents an "average north american driver" on a mix of urban and highway roads, where a lower predicted wear rate generally corresponds to a lower wear prediction accuracy. In fig. 8, the data represents a fleet of city taxis, where the vast majority of miles are in a city driving environment and significantly require higher sampling rates relative to previous data sets.

The results shown in the figures indicate that simple downsampling of data is not a reliable, robust and efficient method of reducing data storage and transmission requirements. The minimum resolution required to achieve a good prediction depends largely on the route being traveled (e.g., city-dominated, or a mix of city and highway) and the manner of driving. In addition, the minimum resolution required also depends on the position of the tire on the vehicle (e.g., left front, right front, etc.).

Thus, as can be appreciated by those skilled in the art, more sophisticated strategies are desired to maximize vehicle dynamics data storage and transmission efficiency for tire wear estimation.

The example tire wear model 134A as disclosed herein may aggregate data from high frequency sources or alternative low frequency sources into low frequency data, such as route data, which may be transmitted to the cloud at this lower frequency in a cost-effective manner, enabling direct wear modeling. In certain implementations, improved efficiency may be achieved with adaptive solutions to make the method more robust and adaptive to field conditions, for example, by encoding wear estimation features into a compressed/reduced data set.

In one embodiment, real-time vehicle dynamics data may be collected from sensors on the vehicle and then filtered and downsampled into a summarized bucket to create a histogram of relevant forces. For example, raw accelerometer data may be downsampled and aggregated into a histogram representing the raw data but at a coarse level.

As represented, for example, in fig. 9, the real-time vehicle dynamics data 310 may be compiled into a window 320 of time and/or distance. Compiled data may also be aggregated into a histogram data frame 330. In the illustrated embodiment, the data frame 330 is multi-dimensional and contains body acceleration and body velocity. Each point in the histogram represents the time or distance spent in that situation. The bins of the histogram may be optimized to maximize wear calculation accuracy and further minimize data storage and transmission costs, for example, to achieve a simple equally spaced or non-linear bin layout.

FIG. 10 shows an example of a histogram data frame having a first dimension associated with lateral vehicle acceleration and a second dimension associated with fore-aft vehicle acceleration. The various points in this example are color coded to represent the time or distance spent in the corresponding situation.

Referring next to fig. 11, since wear is a cumulative process, it is useful to aggregate data between specific events in terms of time and/or distance. Examples of related events may include, but are not limited to: vehicle range, tire tread depth measurement event, tire rotation event, tire installation event, vehicle maintenance event, daily/monthly/yearly summary, mileage summary (5k, 10k, 20k miles, etc.). The histogram data frame 330 allows for flexible and efficient aggregation that can be used on static data in the cloud (after transmission) or transient data on the vehicle (before transmission of the data).

Unfortunately, data from vehicle systems and communication systems is often or even inherently unreliable. Those skilled in the art will appreciate that it is desirable that the design software system be predictable and robust in the event of data loss or corruption. Since wear is an accumulative process, missing data poses a problem for wear calculations. The histogram data frame 330 as disclosed according to the present embodiment allows for an efficient compensation of missing data.

Referring next to fig. 12, a plurality of histogram data frames 330 having missing data subsets therein may be aggregated to generate a partial data frame 430, which may be further corrected by scaling the data frame by an expected number of data frames relative to the collected number of data frames. The result (corrected data frame 440) will be an average of the driver's behavior.

As previously mentioned, and with further reference now to the tire wear modeling flow as represented in fig. 13 and the exemplary real-time model integration as represented in fig. 14, vehicle dynamics sequence data 710 may be acquired using one or more sensors on or associated with the vehicle. The real-time vehicle-tire model 720 may then be used to simulate tire forces on each tire. In addition, a model of the tire may be used to generate the wear rate simulation 730. Both models can be implemented in real-time on time/distance series data or on aggregate data frames. The simulation results of the model may be stored or transmitted in the form of data frames.

The example in FIG. 14 illustrates a real-time simulation of tire force and transmission of a tire force data frame 830. The scope of the present embodiments is not necessarily limited thereto, and one skilled in the art may appreciate alternative strategies for various use cases.

It should be noted that while many of the embodiments as disclosed herein simulate forces on each tire based on vehicle dynamics data, the scope of the present invention is not so limited unless specifically stated otherwise. In other words, it is within the scope of the present invention to provide raw data corresponding to one or more forces applied to at least one tire if such data is available in a given application.

In another embodiment of the method disclosed herein, vehicle dynamics data may be filtered, down-sampled and aggregated into a subset of behavior or "driver severity" values that represent how the vehicle is traveling. These values are extracted from the raw data to specifically capture predetermined wear performance characteristics of the driver's behavior. The extracted behavioral features are further processed by a downstream (e.g., host server based) wear model. According to other embodiments disclosed herein, behavioral values that are features extracted from raw data prior to transmission into the cloud may optionally be supplemented or otherwise supplemented with other forms of aggregated or compressed data.

In another embodiment, low frequency GPS data from the vehicle may be transmitted to a cloud server, where the route is reconstructed with a reverse mapping algorithm and fed into a time series histogram to understand the time spent under various driving conditions (road, turning, braking, etc.). As with the previous embodiments, according to other embodiments disclosed herein, vehicle location data collected or extracted prior to transmission into the cloud may optionally be supplemented or otherwise supplemented with other forms of aggregated or compressed data.

In another embodiment, the low frequency CAN data may be aggregated to count the time spent under various driving conditions for calculating wear states. As with the first two embodiments, according to one or more other embodiments disclosed herein, feature extraction in the form of event-based driving detection prior to transmission into the cloud may optionally be supplemented or otherwise supplemented with other forms of aggregated or compressed data.

In another embodiment, referring now further to fig. 15, a neural network auto-encoder 900 may be implemented to transform and compress the input CAN bus signal 910 in a first (i.e., encoder) layer 920 and further reconstruct the data in a second (i.e., decoder) layer 940 after transmitting the compressed data into the cloud for use by a tire wear model to predict tire performance. As further shown in the three graphs, the first vehicle acceleration data stream (x-axis acceleration as shown in FIG. 16A), the second vehicle acceleration data stream (y-axis acceleration as shown in FIG. 16B), and the vehicle speed data stream (as shown in FIG. 16C) can be compressed and reconstructed to their respective raw signals with very high accuracy. In each figure, the raw and reconstructed data are overlaid to highlight the accuracy.

Neural network autoencoder 900 is well known in the art for achieving data dimension reduction and typically includes multiple pairs of layers. The input layer 910 has a first size that is reduced via the encoding layer 920 and subsequent layers until the intermediate layer 930 is reached, after which the layer size is increased via decoding 940 until the output layer 950 having the first size. An exemplary use of the auto-encoder disclosed herein may differ from conventional arrangements in that it also includes a specialized third (i.e., wear-estimation) layer 960 that is designed and appended to the second layer 950. The special third layer 960 is configured to implement wear rate calculations to transform the raw CAN-bus signal into an instantaneous (actual) wear rate 970. For example, the wear layer may include a proprietary formula containing specific vehicle and tire information related to the physical system. Since the raw vehicle dynamics data signal can be reconstructed with very high accuracy via the first and second layers of the neural network, the additional third (wear-specific) layer can likewise be highly accurate.

This third layer 960 may also enable the first (encoding) layer 920 and the second (decoding) layer 940 to be trained specifically over time for estimating wear. During the training process, the encoding and decoding layers learn to capture and store the most basic information for wear calculations. For example, the estimated instantaneous or predicted wear rate may be compared to the actual wear rate to generate a model error value 980. The feedback loop 990 provides the model error values back to the auto-encoder for use in updating the model weights and biases in the first layer 920 and/or the second layer 940. The third layer 960 will propagate through weights specific to estimating or predicting tire wear.

In other words, the addition of the third layer 960 to the end of the conventional automatic encoder (i.e., after the second layer 940) allows the neural network to learn a representation of how to best transform the CAN bus signal to be used to predict tire wear, whereas the conventional automatic encoder would simply learn a best representation for the direct backlash of the original signal. The data is encoded with an improved encoding layer, as learned over time via, for example, the aforementioned feedback system, in a manner that enables the decoding layer to produce an optimal signal for estimating or predicting tire wear.

The network architecture may enable the network to learn the physically most important signal features and patterns (peaks, valleys, cross-signal relationships, etc.) with respect to wear and efficiently propagate those features through the network.

In another embodiment, the system may be configured to run a fourier transform on the raw data stream and extract the most relevant frequencies. These frequencies and accompanying amplitudes may be further used to reconstruct the complete raw data state after transmission to the cloud.

With further reference to fig. 17-23, another exemplary embodiment as disclosed herein relates to the use of bayesian methods in the characterization and prediction of tire wear. The method is based on expressing the factors that contribute to wear (such as driving style, vehicle alignment settings, course, road surface, environmental conditions, tire manufacturing variations, etc.) as a probability distribution. The rationale for representing these as probability distributions is that the observed changes in each of these factors are not noise, but rather truly represent the natural changes observed for wear. For example, the same tire used by a aggressive first driver (who is accelerating and braking hard) will experience a very different tire wear life span than a more careful second driver. When used with conventional predictive models, the average representation of these two drivers will yield a prediction that is not sufficient when applied to either situation alone.

The effect of this probabilistic representation of the contributing factors is that the prediction by the wear algorithm will also be probabilistic, i.e. the prediction will also be a distribution. When reporting predictions, the use of distributions has several benefits. First, the predictions may give them a measure of uncertainty, i.e., 4.1mm +/-0.05mm tread wear, or 55,000 miles +/-3000 miles (these two ranges may correspond to particular confidence levels, such as 95% or 98%). Second, bayesian inference can be used to update these distributions based on observations. Such observations may be, for example, for predicted variables (e.g., a measurement of tread depth) or input variables (acceleration characterizing driving style). This inferred value may be because the model or associated system, as described further below, may continue to update the predictions and the confidence of such predictions over time relative to, for example, a specified travel distance or the time taken to travel using an associated tire.

Referring to the schematic in fig. 18, an exemplary process flow may be illustrated by comparison with a conventional method as shown in fig. 17. A probability distribution of tire wear related factors, such as vehicle wheel and suspension settings, can be generated and fed into a vehicle model, as opposed to specific target or measured values for the same factors. One example of such a factor is camber angle, also known as the angle from the normal of the road surface through the center of the respective wheel (on which the tire is mounted) to the centerline of the wheel. Another example of such a factor is toe angle, also referred to as the angle of the tire relative to the longitudinal axis of the respective vehicle.

From these initial ranges, additional probability distributions may be generated about or otherwise corresponding to each of a plurality of correlated forces (e.g., traction or longitudinal force Fx, lateral force Fy, vertical or normal force Fz) and/or moments (e.g., overturning torque My, alignment torque Mz) on the associated tire, again as opposed to individual values of the same force. The force profile may be fed into a tire wear model where the tread depth is estimated for a given travel distance (e.g., 15000km) under a calculated uncertainty range (e.g., +/-0.3mm) from a baseline value (e.g., 5.8mm), as opposed to just the baseline value.

Subsequently, the probability distribution of tread depths may be updated based on the observations, as shown above with the schematic. This update may be implemented using a representation of Bayesian theorem, which is shown here:

bayesian filtering methods are known in the art for determining the likelihood of a given measurement from, for example, all previous corresponding measurements in the sensor data stream. Here, the term "model" refers to the parameters of the model, and the term "observations" refers to measurements made on any/all variables involved in the model. According to the above formula, the information related to tire wear prediction may be updated over time using actual measurements. In other words, using this approach, the model prediction can be "corrected" with each measurement made for a particular tire component and/or vehicle tire system. For example, if tread depth measurements are periodically collected and transmitted or otherwise compiled for application in accordance with the systems and methods disclosed herein, such measurements may be implemented to reduce uncertainty and enable better predictions over time.

Referring next to fig. 19, tire wear prediction corrections may be provided periodically along with tread depth measurements, with the uncertainty of the wear prediction being correspondingly reduced. When measurements of tread depth (or equivalent tire wear related factors) are collected over time, potential alternative models or time series curves can be effectively excluded or minimized for a given tire, vehicle driver-tire system, etc., and subsequent tire wear estimates can be provided more accurately with less uncertainty in their respective results.

As shown, the wear prediction curve proceeds from a first point (along the y-axis) with a surrounding wear prediction uncertainty U0. After subsequent tread depth measurements, a corrected wear prediction curve is generated, along with a reduced level of uncertainty U1 of the wear prediction. In this example, the second envelope of uncertainty U1 falls completely within the first envelope. After another tread depth measurement, a third and further corrected wear prediction curve is generated, along with a further reduced level of uncertainty U2 in the wear prediction.

Referring next to fig. 20 and 21, an exemplary application of the monte carlo method is illustrated to construct probability distributions and use these distributions to generate wear progress curve distributions (see, for example, the wear progress curves for the exemplary front tire as shown in fig. 22 and the wear progress curves for the exemplary rear tire as shown in fig. 23). In other words, for a given change in vehicle alignment setting, the method attempts to determine a corresponding change in wear progress. In the particular illustrated case, it is assumed that the input is a normal distribution that is independent only for toe and camber angles, with all other factors being referred to as single points. While toe and camber angles have been selected herein for illustration, it should be understood that alternative or additional vehicle and/or tire arrangements may be applicable to tire wear models, and thus be implemented by the systems and methods as disclosed herein, unless specifically noted otherwise.

Referring in particular to the rear tire progression curve in fig. 23, the central curve represents the nominal toe/camber setting, with the surrounding areas representing ten thousand individual wear progression curves corresponding to respective initial wear rates Ew. It can be observed that as the mileage increases, the change in wear progress increases accordingly. By enabling periodic measurements of the values of the base factors, an appropriate subset of each wear progress curve may be identified with increasing certainty over time, wherein tire wear states may be accurately predicted with only a relatively small number of actual measurements.

Thus, even periodic measurements of tread depth or other related factors provide real-time feedback to a user (e.g., fleet administrator, end user) and enhance the ability to predict the remaining wear life of a tire and further maximize the remaining value of the tire.

Periodic measurements associated with tire wear (e.g., tire tread depth) for the supplemental probability distributions can be directly made (manually by a user and/or via one or more sensors) and/or estimated according to tire wear models and techniques as otherwise described herein.

With further reference to fig. 24-26, another exemplary embodiment of a method as disclosed herein involves the use of brush type analysis in characterizing and predicting tire wear. The brush model is a simplified tire model with a logical-physical background that models tread elements as individual "bristles" extending outward from the base material (e.g., the carcass) of the tire. The brush model greatly reduces the complexity of modeling the contact interface between the road surface and the base material, where the modeled tread elements can deform in various measurable directions (e.g., longitudinal, lateral, vertical) and can capture the first order effects (tread block hardening and contact area increase) that occur in a real tire as it wears. In alternative embodiments, characterization and prediction of tire wear may be accomplished using other physics-based tire wear models, such as, for example, Finite Element Analysis (FEA).

One embodiment of the method as disclosed herein also advantageously predicts the absolute wear rate of a tire under a given condition, not just how the wear rate changes with decreasing tread depth. This is accomplished, at least in part, by normalizing the current modeled wear rate (e.g., based on periodically or otherwise updated measurements) with respect to the wear rate at the original tread depth (i.e., the initial wear rate).

Referring to the graphical diagram in, for example, fig. 24, an exemplary output of the model is shown, where on the y-axis is the normalized wear rate ratio for two different tires and on the x-axis is the tread loss for the two different tires. The initial wear rate may be provided as an input to the system, such as, but not limited to, from the FEA phase, machine learning models, etc., which may predict tread depth progression over the life of a given tire.

Referring next to fig. 25, an exemplary set of results when simulating a worn reference tire using the predictive method is shown compared to measured data for the same tire/vehicle-tire system via outdoor wear testing. The circular markers indicate the average tread depth of the control tire test results at each inspection mile, while the lower solid line represents the predicted tread depth relative to the initial tread depth and further normalized via the brush model.

The validation data as further represented in fig. 26 also indicates an acceptable model fit for an exemplary tire wear model, such as a hybrid brush model as disclosed herein. In this case, the difference between the predicted result of a certain control tire and the indoor wear test result is less than 0.25mm for each mileage of the inspected tread depth.

The hybrid brush model as disclosed herein is extremely fast and efficient, and can be executed substantially in real time. Test results to date indicate that the model accurately predicts the wear progression for very different tire designs. Only a relatively small subset of inputs is required, such as, for example, the original tread depth and the contact/void area at various tread depths. This information may be taken from, for example, a 3D model of the tread pattern, or from Circumferential Tread Wear Imaging System (CTWIST) measurements of the tire, typically provided for each tire for indoor or outdoor wear testing.

In one embodiment, other tire related threshold events may be predicted and implemented for alarm and/or intervention within the scope of the present disclosure. For example, the system may identify other services recommended for a given vehicle based on time series input received and processed as described above, predicted tire wear, and the like. Examples of such services may include, but are not limited to, tire rotation, alignment, inflation, and the like. The system may generate an alert and/or intervention recommendation based on various threshold, set of thresholds, and/or non-threshold algorithmic comparisons with respect to predetermined parameters.

In one embodiment, it is within the scope of the present disclosure that the optimal type of tire and/or tire parameter may be predicted and implemented for alarm and/or intervention. For example, the system may identify a vehicle application (higher city driving example, higher highway driving example, etc.) and/or driving style based at least in part on the time series input, predicted tire wear, etc., received and processed as described above. The system may determine that certain tires are more suitable for a given vehicle based not only on the type of vehicle, but also on the identified vehicle application and/or driving style, and also generate alerts and/or intervention recommendations based at least in part thereon.

As previously described, tire information may be provided from one or more sensors mounted on a given tire or associated vehicle. The one or more sensors may be accelerometers mounted directly on, for example, the inner liner of a tire or the spindle of a vehicle. Output signals from the sensors may be provided to the hosted server, e.g., without input from a user.

Referring now more particularly to fig. 27-29, another exemplary technique for estimating the tread depth of a tire is disclosed herein. As can be appreciated by those skilled in the art, as a tire wears and loses mass, the modal frequencies change in a manner that is directly or can be correlated with mass loss. This principle is clear when considering a single degree of freedom mass-spring system, where the natural frequency is equal to the square of the spring rate divided by the mass. As the mass decreases, the natural frequency increases. Using this same principle for the structural mode of the tire, the mass loss can be determined based on modal frequency shifts by:

where Δ m is the mass change, m is the mass when the tire is new, and ω n is the natural frequency.

Modal frequencies can be identified by several methods, including (as previously described) attaching an accelerometer to a tire, or attaching an accelerometer to a spindle of a vehicle. Tire structure modes may also be activated in a variety of ways, including, for example, controlled impact of an object (such as a hammer, kicking a tire, etc.) on the tire, electrical activation, crossing over obstacles (such as cleats or speed bumps), and/or running a vehicle-tire combination over a rough surface. In certain embodiments, the random excitation event may occur during operation of the vehicle-tire combination, wherein output signals from the sensors may be collected and stored and/or processed to estimate tire wear.

Fig. 27 shows an example from a static natural frequency test, where a given tire is impacted by a hammer, and an accelerometer is attached to the inner liner of the tire. The vibrations associated with the shock produce an output signal from the accelerometer having a Power Spectral Density (PSD) waveform as shown. The PSD waveform for a given impulse represents the frequency distribution of the associated output signal. The accelerometer may be configured to provide an output voltage that may be converted by the signal processing circuitry into an equivalent acceleration signal. These time domain signals may themselves be further transformed into the frequency domain using, for example, a fast fourier transform. The frequency response function in the power spectrum may typically contain size information expressed in decibel (dB) scales.

Corresponding peaks in the frequency spectrum from the respective waveforms for the new and worn states of a given tire are highlighted to illustrate the frequency shift due to tread loss between the two. In this example, the mass loss calculated according to the above formula is 0.474 kilograms (kg), which is substantially the same as the actual measurement of 0.467 kg. In various embodiments, additional steps may be implemented to correlate mass loss with tread loss, or alternatively, correlation of modal frequency shift with respect to tread depth may be performed more reliably for a given tire.

Finite Element Analysis (FEA) simulations were also performed showing similar frequency shifts from, for example, both transmission rate testing (where the matrix is excited by random input) and cleat impact (where the tire is rolling on the cleat).

Fig. 28A represents results from a cleat impact simulation for a new tire, where the first graph shows vertical force variation over time and the second graph shows Fast Fourier Transform (FFT) magnitude over a frequency range (in Hz).

Fig. 28B represents the corresponding results from the cleat impact simulation for the same tire in a worn state, where the modal frequency shift can be easily observed between the new state and the worn state.

FIG. 29 represents the results of a transmission simulation from a new state and a worn state of a given tire, showing the transmission (in dB) relative to the frequency spectrum, again where a modal frequency shift is readily observable between the new state and the worn state, and where this frequency shift is applicable to estimate changes in quality and correspondingly tire wear/tread depth.

In each of the foregoing exemplary cases, the results shown are for the same tire, with the same frequency shift observed between the worn tire model and the new tire model, and implemented in the disclosed tire wear model.

Throughout the specification and claims, the following terms take at least the meanings explicitly associated herein, unless the context dictates otherwise. The meanings identified below do not necessarily limit the terms, but merely provide illustrative examples for the terms. The meaning of "a", "an", and "the" may include plural references, and the meaning of "in. As used herein, the phrase "in one embodiment" does not necessarily refer to the same embodiment, although it may.

The various illustrative logical blocks, modules, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. The described functionality may be implemented in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The various illustrative logical blocks and modules described in connection with the embodiments disclosed herein may be implemented or performed with a machine such as a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be a controller, microcontroller, or state machine, combinations of these, or the like. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

The steps of a method, process, or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of computer-readable medium known in the art. An exemplary computer readable medium can be coupled to the processor such the processor can read information from, and write information to, the memory/storage medium. In the alternative, the medium may be integral to the processor. The processor and the medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the medium may reside as discrete components in a user terminal.

Conditional language (such as "may," "e.g.," etc.) as used herein is generally intended to convey that certain embodiments include certain features, elements, and/or states, while other embodiments do not include certain features, elements, and/or states, unless specifically stated otherwise or otherwise understood within the context of use. Thus, such conditional language is not generally intended to imply that features, elements, and/or states are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without author input or prompting, whether such features, elements, and/or states are included or are to be performed in any particular embodiment.

While certain preferred embodiments of the present invention may be described herein generally with respect to tire wear and/or tire traction estimation for fleet management systems and more specifically autonomous vehicle fleet or commercial truck applications, the present invention is expressly by no means limited thereto, and unless otherwise specified, the term "vehicle" as used herein may refer to automobiles, trucks, or any equivalent thereof (whether self-propelled or otherwise) that may include one or more tires and thus require accurate estimation or prediction of tire wear and/or tire traction and potential disablement, replacement, or intervention in the form of, for example, direct vehicle control adjustments.

Unless otherwise specified, the term "user" as used herein may refer to a driver, passenger, mechanic, technician, fleet manager, or any other person or entity that may be associated, for example, with a device having a user interface for providing features and steps as disclosed herein.

The foregoing detailed description has been presented for purposes of illustration and description. Thus, while particular embodiments of the new and useful invention have been described, it is not intended that such references be construed as limitations upon the scope of this invention except as set forth in the following claims.

Claims

1. A computer-implemented method, comprising:

collecting vehicle data of a vehicle and/or tire data of at least one tire associated with the vehicle;

determining a current tire wear state of the at least one tire in real time based at least in part on the collected data;

predicting one or more tire performance characteristics based, at least in part, on the determined tire wear state and the collected data; and

selectively providing real-time feedback based on the predicted one or more tire performance characteristics and/or the determined current tire wear state.

2. The method of claim 1, wherein:

accumulating, in a data storage device, information about a probability distribution corresponding to each tire wear factor of a respective plurality of tire wear factors;

transmitting the collected vehicle data and/or tire data from the vehicle to a remote server;

generating at least one observation corresponding to one or more of the plurality of factors based on the transmitted vehicle data and/or tire data; and is

A bayesian estimate of the current tire wear state of the at least one tire associated with the vehicle is provided based at least on the generated at least one observation and the stored information about the probability distribution.

3. The method of claim 2, further comprising storing information regarding updated probability distributions corresponding to a respective plurality of factors contributing to tire wear for the at least one tire associated with the vehicle based at least on the generated at least one observation.

4. The method of claim 2 or claim 3, wherein the one or more tire wear characteristics predicted comprise predicted tire wear states over one or more future times of the at least one tire associated with the vehicle.

5. The method of claim 4, wherein the one or more tire wear characteristics predicted comprise a replacement time of the at least one tire associated with the vehicle based on a current tire wear state or a predicted tire wear state as compared to a tire wear threshold associated with the at least one tire associated with the vehicle.

6. The method of claim 2, wherein the information about the plurality of probability distributions reflects a time series relational array.

7. The method of any of claims 2, 3, or 6, further comprising:

receiving, from a user via a user interface associated with the remote server, one or more tire wear input values, and/or one or more tire wear input values generated by one or more sensors mounted in or on respective ones of the at least one tire, and/or one or more tire wear input values generated by sensors external to the vehicle; and

generating at least one observation of one or more of the plurality of factors based on the one or more tire wear input values.

8. The method of claim 7, wherein:

at least one of the tire wear input values generated by the sensor external to the vehicle comprises a tread depth measurement.

9. The method of claim 2, further comprising:

generating an estimated tire wear state using a baseline value and a range corresponding to the estimated confidence level.

10. The method of claim 1, comprising:

determining an original tread depth of a tire associated with a vehicle;

determining an initial wear rate of the tire based at least in part on the original tread depth;

measuring one or more tire conditions as a time series input to a predictive tire wear model and generating a current wear rate for the tire further based on the time series input;

normalizing the current wear rate to the initial wear rate of the tire; and

predicting a tire wear state of the tire for one or more specified future parameters.

11. The method of claim 10, wherein:

the current wear rate is also determined based on a brush tire wear model for a contact interface between a base material of the tire and a road surface, where the interface is represented as a plurality of independently deformable elements.

12. The method of any one of claim 10 or claim 11, wherein:

the measured one or more tire conditions include a detected contact area and a void area corresponding to a tire tread depth.

13. The method of any one of claim 10 or claim 11, wherein:

the one or more specified future parameters are associated with one or more of a travel time and a travel distance.

14. The method of any one of claim 10 or claim 11, comprising:

predicting a replacement time for the tire based on the predicted tire wear state as compared to one or more predetermined tire wear thresholds associated with the tire.

15. The method of claim 14, further comprising generating an alert to a user associated with the vehicle based on the predicted replacement time.

16. The method of claim 10, further comprising:

receiving the measured conditions from a user inputting one or more measured conditions via a user interface and/or from one or more sensors mounted in or on the tire and/or from a sensor external to the vehicle.

17. The method of claim 10, further comprising:

predicting a tire rotation threshold event and/or an alignment threshold event, and based thereon, generating an alert to a user interface associated with the vehicle.

18. The method of claim 10, further comprising:

predicting an optimal tire type for the vehicle based at least in part on the time series input, an

Based thereon, an alert is generated to a user interface associated with the vehicle.

19. The method of claim 1, comprising:

storing a tread depth of a tire associated with a vehicle over a first stage;

sensing and storing a first set of one or more modal frequencies of the tire over the first phase in response to a first modal analysis for the tire;

sensing, on a subsequent second stage, a second set of corresponding one or more modal frequencies of the tire in response to a second modal analysis for the tire; and

estimating a tire wear state of the tire over the second stage based on the calculated frequency shift between at least one corresponding modal frequency from each of the first and second sets.

20. The method of claim 19, further comprising:

storing a mass of the tire over the first phase, wherein the step of estimating the tire wear state over the second phase comprises determining a change in the mass of the tire between the first phase and the second phase based on the calculated frequency shift.

21. The method of claim 20, wherein:

determining an estimated loss of tire tread relative to the change in mass of the tire between the first stage and the second stage based on the calculated frequency shift.

22. The method of claim 20, wherein:

an estimated loss of tire tread is determined via a retrievable correlation between the observed frequency shift and a change in tire tread for a given tire.

23. The method of claim 22, wherein:

the correlation is retrieved from a data storage device for a given tire type.

24. The method of claim 22, wherein:

the correlation is established over time based on historical measurements of changes in tire tread and shifts between corresponding modal frequencies associated with the given tire type.

25. The method of any one of claims 19 to 24, wherein:

sensing, via one or more accelerometers, the first and second sets of corresponding modal frequencies in response to excitation of a structural mode of the tire.

26. The method of claim 25, wherein:

randomly exciting the tire structure mode during operation of the tire and capturing associated output signals generated by the one or more accelerometers.

27. The method of claim 25, wherein the tire structural mode is excited by a controlled impact of an external object on the tire.

28. The method of claim 25, wherein the tire structure mode is excited by directing movement of the vehicle relative to one or more predetermined obstacles.

29. The method of claim 1, wherein:

the predicted one or more tire performance characteristics include a tire traction characteristic of the at least one tire; and

providing the real-time feedback for automatically modifying one or more vehicle operation settings based at least on the predicted one or more tire traction characteristics.

30. The method of claim 29, further comprising:

determining a maximum speed of the vehicle based at least on the transmitted vehicle data and the determined tire wear state for each tire associated with the vehicle; and

providing the maximum speed to an autonomous vehicle control system associated with the vehicle and/or a driver assistance interface associated with the vehicle.

31. The method of claim 29, wherein the step of determining the tire wear state comprises:

receiving one or more tire wear input values from a user via a user interface;

receiving one or more tire wear input values generated by one or more sensors mounted in or on respective ones of the at least one tire;

receiving one or more tire wear input values generated by a sensor external to the vehicle; and/or

Predicting one or more tire wear input values based at least on the transmitted vehicle data and tire data generated by one or more sensors mounted in or on respective ones of the at least one tire.

32. The method of claim 1, wherein:

the collecting vehicle data comprises generating first data corresponding to real-time dynamics of a vehicle and/or at least one tire of a plurality of tires supporting the vehicle via one or more sensors associated with the vehicle and/or the at least one tire;

the first data is processed to generate second data as a reduced subset of the first data, the second data representing the first data and including any one or more predetermined features extracted therefrom; and is

The second data is processed to estimate a wear characteristic of the at least one tire.

33. The method of claim 32, wherein the first data is processed via a computing system on the vehicle, the method further comprising:

selectively transmitting the second data to a remote computing system via a communication network; and

processing, via the remote computing system, the second data to estimate the wear characteristic of the at least one tire.

34. The method of claim 33, wherein:

the second data comprises a plurality of sequential data frames, each data frame comprising a multi-dimensional histogram of forces associated with the vehicle and/or the at least one tire.

35. The method of claim 34, further comprising:

selecting a subset of the data frames at least between a first event and a second event; and

the data frames are summarized at a particular time or over a particular distance.

36. The method of claim 35, wherein:

performing the aggregation of the data frames via local processing prior to transmitting the aggregated data frames to the remote computing system.

37. The method of claim 35, wherein:

transmitting the subset of the data frame to the remote computing system, and

performing, via the remote computing system, the aggregation of the data frames.

38. The method of any of claims 35 to 37, further comprising:

missing data in the summarized data frames is corrected by scaling the summarized data frames by an expected number of data frames relative to an actual collected number of data frames.

39. The method of any one of claims 33 to 37, wherein the step of processing the second data to estimate the wear characteristic of the at least one tire comprises:

processing, via the remote computing system, the second data to generate third data corresponding to the first data; and

the third data is also processed to estimate the wear characteristic of the at least one tire.

40. The method of claim 39, wherein:

the first data comprises a CAN-bus signal,

the second data is generated via an encoding neural network layer,

the third data is generated via a decoding neural network layer, and

a wear calculation layer is appended to an output of the decoding neural network layer and configured to transform the decoded CAN bus signal into an instantaneous estimated wear value for the at least one tire.

41. The method of claim 40, further comprising:

comparing the estimated wear value and an actual wear value of the at least one tire to generate an error value; and

providing the error value as feedback to the neural network layer.

42. The method of any one of claims 32 to 37, wherein:

the extracted features of the second data include wear performance characteristics indicative of vehicle driving behavior.

43. The method of any one of claims 32 to 37, wherein:

processing the first data includes fourier transforming the first data and generating the second data including the extracted correlated frequencies and associated amplitudes.

44. The method of claim 32 or 33, wherein the second data comprises aggregated low frequency CAN data corresponding to an amount of time the vehicle spends in each of one or more representative driving conditions.

45. The method of claim 32 or 33, wherein:

the selective transmission of the second data is event-based and/or time-based.

46. The method of claim 32, wherein the first data is processed via a computing system on the vehicle, the method further comprising:

processing, via an on-board computing system, the second data to estimate the wear characteristic of the at least one tire; and

a notification associated with the estimated wear characteristic is generated to a display unit associated with a user of the vehicle.

47. The method of claim 46, wherein the step of processing the second data to estimate the wear characteristic of the at least one tire comprises:

processing the second data to generate third data corresponding to the first data; and

48. The method of claim 47, wherein:

the first data comprises a CAN-bus signal,

the second data is generated via an encoding neural network layer,

the third data is generated via a decoding neural network layer, and

49. The method of claim 48, further comprising:

providing the error value as feedback to the neural network layer.

50. The method of claim 1, wherein the collecting vehicle data comprises generating first data corresponding to real-time dynamics of a vehicle and/or at least one tire of a plurality of tires supporting the vehicle via one or more sensors associated with the vehicle and/or the at least one tire; the method further comprises the following steps:

generating, via a global positioning system transceiver, low frequency second data corresponding to the vehicle location;

selectively transmitting the second data to a remote computing system via a communication network;

processing, via the remote computing system, the second data further in accordance with a vehicle model and one or more vehicle route characteristics to generate third data corresponding to the first data, and also processing the third data to estimate the wear characteristic of the at least one tire.

51. The method of claim 50, wherein:

the second data further comprises a plurality of sequential data frames, each data frame comprising a multi-dimensional histogram of forces associated with the vehicle and/or the at least one tire, and

the remote computing system reconstructs a vehicle route from the collected vehicle position data and provides vehicle route feedback into the respective multi-dimensional histogram.